SOTAVerified

Active Learning

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2231–2240 of 3073 papers

TitleStatusHype
Investigating Active Learning and Meta-Learning for Iterative Peptide Design—0
Rethinking deep active learning: Using unlabeled data at model trainingCode0
Bias-Aware Heapified Policy for Active Learning—0
Online Adaptive Asymmetric Active Learning with Limited BudgetsCode0
The Effectiveness of Variational Autoencoders for Active Learning—0
Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition—0
Active learning in the geometric block model—0
Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision—0
Cost-efficient segmentation of electron microscopy images using active learning—0
Incentive Compatible Active Learning—0
Show:102550
← PrevPage 224 of 308Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TypiClustAccuracy93.2—Unverified
2PT4ALAccuracy93.1—Unverified
3Learning lossAccuracy91.01—Unverified
4CoreGCNAccuracy90.7—Unverified
5Core-setAccuracy89.92—Unverified
6Random Baseline (Resnet18)Accuracy88.45—Unverified
7Random Baseline (VGG16)Accuracy85.09—Unverified